© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 137133
    Prev
    Next
    INDEX
    Explanations

    why should i care about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_12_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     चांगले
    0.71
     चांगली
    0.64
    蒉
    0.60
    ceso
    0.60
    Todas
    0.60
     භාවිතා
    0.59
    Hilo
    0.58
    )،
    0.58
    ,}
    0.58
     appelez
    0.58
    POSITIVE LOGITS
    ↵
    0.71
     leg
    0.61
     waste
    0.58
     care
    0.55
     sod
    0.55
     laundry
    0.54
     junk
    0.53
     wine
    0.52
     sleeping
    0.52
    ले
    0.51
    Activations Density 0.002%

    No Known Activations